upgini 1.1.301__py3-none-any.whl → 1.1.303__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.1.301"
+__version__ = "1.1.303"

upgini/data_source/data_source_publisher.py

@@ -82,6 +82,9 @@ class DataSourcePublisher:
 
         date_format - optional str - format of date if it is present in search keys
 
+        features_for_embeddings - optional list of str - list of features that should be used for GPT features
+            generation
+
         ...
 
         data_table_id_to_replace - optional str - id of registered ADS that should be replaced by new table

upgini/features_enricher.py

@@ -3483,6 +3483,9 @@ class FeaturesEnricher(TransformerMixin):
         is_transform=False,
         silent_mode=False,
     ):
+        for _, key_type in search_keys.items():
+            if not isinstance(key_type, SearchKey):
+                raise ValidationError(self.bundle.get("unsupported_type_of_search_key").format(key_type))
         valid_search_keys = {}
         unsupported_search_keys = {
             SearchKey.IP_RANGE_FROM,

upgini/metadata.py

@@ -191,7 +191,7 @@ class FileColumnMetadata(BaseModel):
     # is this column contains keys from multiple key columns like msisdn1, msisdn2
     isUnnest: bool = False
     # list of original etalon key column names like msisdn1, msisdn2
-    unnestKeyNames: Optional[list[str]]
+    unnestKeyNames: Optional[List[str]]
 
 
 class FileMetadata(BaseModel):

upgini/resource_bundle/strings.properties

@@ -85,6 +85,7 @@ unregistered_only_personal_keys=Only personal search keys used. Api_key from pro
 search_key_not_found=Column `{}` from search_keys was not found in X dataframe: {}
 numeric_search_key_not_found=Index {} in search_keys is out of bounds for {} columns of X dataframe
 unsupported_search_key_type=Unsupported type of key in search_keys: {}
+unsupported_type_of_search_key=Unsupported type of search key: {}. It should be a member of SearcKey
 search_key_country_and_country_code=\nWARNING: SearchKey.COUNTRY and country_code parameter were passed simultaniously. Parameter country_code will be ignored
 empty_search_key=Search key {} is empty. Please fill values or remove this search key
 single_constant_search_key=\nWARNING: Constant value detected for the {} search key in the X dataframe: {}.\nThat search key will add constant features for different y values.\nPlease add extra search keys with non constant values, like the COUNTRY, POSTAL_CODE, DATE, PHONE NUMBER, EMAIL/HEM or IPv4

upgini/utils/datetime_utils.py

@@ -31,7 +31,7 @@ DATE_FORMATS = [
     "%Y-%m-%dT%H:%M:%S.%f",
 ]
 
-DATETIME_PATTERN = r"^[\d\s\.\-:T]+$"
+DATETIME_PATTERN = r"^[\d\s\.\-:T/]+$"
 
 
 class DateTimeSearchKeyConverter:
@@ -147,7 +147,10 @@ class DateTimeSearchKeyConverter:
                     return pd.to_datetime(df[self.date_column], format=date_format)
                 except ValueError:
                     pass
-            raise ValidationError(self.bundle.get("invalid_date_format").format(self.date_column))
+            try:
+                return pd.to_datetime(df[self.date_column])
+            except ValueError:
+                raise ValidationError(self.bundle.get("invalid_date_format").format(self.date_column))
 
 
 def is_time_series(df: pd.DataFrame, date_col: str) -> bool:

{upgini-1.1.301.dist-info → upgini-1.1.303.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.301
+Version: 1.1.303
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/

{upgini-1.1.301.dist-info → upgini-1.1.303.dist-info}/RECORD

@@ -1,12 +1,12 @@
-upgini/__about__.py,sha256=L11AcDL4xom7Zln7UryeDX6XjWGUw7VdTIlPlnfMwTc,24
+upgini/__about__.py,sha256=DZ-j6x_TqRaD5W2xKCfhOLDmhOQuGblZWwKIzlYBLkg,24
 upgini/__init__.py,sha256=ObEtjFkIssl83qeKNMLpIQygfwK8TzztwiI43YTsAP0,353
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=MOzBVsvzlHLxNfPWtMaXC_jIPeW7_gUvbSGeXnsPgNI,46158
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=OW3aQ0vyaKMrxWBhptdvb_SAxNqf7H6jssOFdfW20mc,183136
+upgini/features_enricher.py,sha256=PRiQGAmnm9jPXN4Uqus5l8RQIPAWPxsIBnIoEMnh6g8,183342
 upgini/http.py,sha256=bp6jWl422Icy3AhHMdCcJv5NjExE45gSMmzMTPJjPuk,42600
 upgini/lazy_import.py,sha256=EwoM0msNGbSmWBhGbrLDny1DSnOlvTxCjmMKPxYlDms,610
-upgini/metadata.py,sha256=wOFCJruDBhC4Hiiiqf8GeHZnnm6rhJy8t6fg5B0Z4TQ,10209
+upgini/metadata.py,sha256=E5WWZ_MkjGyYNQh_LnwMIBHyqPx1fxk-qhEfQIJnzq8,10209
 upgini/metrics.py,sha256=Tu5cN8RlhOSSMWUTXRSkdl8SWBqR1N_2eJpBum9pZxc,30926
 upgini/search_task.py,sha256=LtRJ9bCPjMo1gJ-sUDKERhDwGcWKImrzwVFHjkMSQHQ,17071
 upgini/spinner.py,sha256=4iMd-eIe_BnkqFEMIliULTbj6rNI2HkN_VJ4qYe0cUc,1118
@@ -23,14 +23,14 @@ upgini/autofe/operand.py,sha256=MKEsl3zxpWzRDpTkE0sNJxTu62U20sWOvEKhPjUWS6s,2915
 upgini/autofe/unary.py,sha256=ZWjLd-CUkNt_PpM8YuWLLipW1v_RdBlsl4JxXIVo9aM,3652
 upgini/autofe/vector.py,sha256=dLxfAstJs-gw_OQ1xxoxcM6pVzORlV0HVzdzt7cLXVQ,606
 upgini/data_source/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-upgini/data_source/data_source_publisher.py,sha256=1cQZrK630VztwGGDp41ec9gqIeUtkefaqSSQEitVWiM,19581
+upgini/data_source/data_source_publisher.py,sha256=aCVpZ3RGlYToRYYNHjC2BxIxnnKUyrrF29MncCXhVlE,19716
 upgini/mdc/__init__.py,sha256=aM08nIWFc2gWdWUa3_IuEnNND0cQPkBGnYpRMnfFN8k,1019
 upgini/mdc/context.py,sha256=3u1B-jXt7tXEvNcV3qmR9SDCseudnY7KYsLclBdwVLk,1405
 upgini/normalizer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/normalizer/phone_normalizer.py,sha256=EzTaahk6myRv6ZXgbyVFGY4kpo_2VlQgOrm5_lfbmNI,9996
 upgini/resource_bundle/__init__.py,sha256=S5F2G47pnJd2LDpmFsjDqEwiKkP8Hm-hcseDbMka6Ko,8345
 upgini/resource_bundle/exceptions.py,sha256=5fRvx0_vWdE1-7HcSgF0tckB4A9AKyf5RiinZkInTsI,621
-upgini/resource_bundle/strings.properties,sha256=6jYqcxj06ZopXwr5YYMGXX1QiNNJNFo2SuwAR0qleRk,26358
+upgini/resource_bundle/strings.properties,sha256=WZAuYPX2Dpn6BHoA3RX8uvMNMr-yJE2fF7Gz0i24x2s,26459
 upgini/resource_bundle/strings_widget.properties,sha256=gOdqvZWntP2LCza_tyVk1_yRYcG4c04K9sQOAVhF_gw,1577
 upgini/sampler/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/sampler/base.py,sha256=7GpjYqjOp58vYcJLiX__1R5wjUlyQbxvHJ2klFnup_M,6389
@@ -42,7 +42,7 @@ upgini/utils/blocked_time_series.py,sha256=Uqr3vp4YqNclj2-PzEYqVy763GSXHn86sbpIl
 upgini/utils/country_utils.py,sha256=yE8oRgMpXuJxPfQm4fioY6dg6700HgVnHSk4Cv9sUyM,6511
 upgini/utils/custom_loss_utils.py,sha256=kieNZYBYZm5ZGBltF1F_jOSF4ea6C29rYuCyiDcqVNY,3857
 upgini/utils/cv_utils.py,sha256=w6FQb9nO8BWDx88EF83NpjPLarK4eR4ia0Wg0kLBJC4,3525
-upgini/utils/datetime_utils.py,sha256=Ujmu1ouwSFtG5SywQXJlmtDnGigAnIWPdE5Vx5NvgUM,10951
+upgini/utils/datetime_utils.py,sha256=uJ3wJNr4KQvDJ-gSOLcmP85hLtASK271o6mob4aZT90,11064
 upgini/utils/deduplicate_utils.py,sha256=Zvs7zW4QzaERQmJNPrTVf2ZTVBkBLOycFCzyMwtXuV8,8770
 upgini/utils/display_utils.py,sha256=A2ouB5eiZ-Kyt9ykYxkLQwyoRPrdYeJymwNTiajtFXs,10990
 upgini/utils/email_utils.py,sha256=aKHa4xVBSsEsiZtFCPj_DrUaFupceYfvJeP_e8w_D5E,3813
@@ -57,7 +57,7 @@ upgini/utils/sklearn_ext.py,sha256=13jQS_k7v0aUtudXV6nGUEWjttPQzAW9AFYL5wgEz9k,4
 upgini/utils/target_utils.py,sha256=Y96_PJ5cC-WsEbeqg20v9uqywDQobLoTb-xoP7S3o4E,7807
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/warning_counter.py,sha256=dIWBB4dI5XRRJZudvIlqlIYKEiwLLPcXarsZuYRt338,227
-upgini-1.1.301.dist-info/METADATA,sha256=DzWKpZGrQ1cMxlEFVzE0GFg3Zl64sJvjYydjx4u6xhA,48153
-upgini-1.1.301.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.1.301.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.1.301.dist-info/RECORD,,
+upgini-1.1.303.dist-info/METADATA,sha256=4RboHCgNVmHfmPnjut5UyMzn9qd7AMlCsBWnfk8QD0s,48153
+upgini-1.1.303.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.1.303.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.1.303.dist-info/RECORD,,